Automate browser tasks directly in your own Chrome. No need to start a separate browser. This skill uses the agent-browser tool to control your real browser session. It can navigate pages, fill forms, click buttons, and take screenshots. It also extracts data and replays recorded workflows.
The key idea is to reuse your existing open tabs. That way you keep your login sessions and cookies. You avoid extra logins and wasted time. The tool always lists your open tabs first. Then it switches to a tab if your page is already there. If not, it opens a new page.
This skill works with your real browser state. No separate profiles or fresh browsers. Just connect and go.
Global
mkdir -p ~/.claude/skills/chrome-automationProject
mkdir -p .claude/skills/chrome-automationSource Repository
Agent Browservercel-labs/agent-browser
Fast browser automation tool for AI agents to control any website
Develop Userscriptsxixu-me/skills
Build and debug browser userscripts for Tampermonkey and ScriptCat
Just Scrapescrapegraphai/just-scrape
Search, scrape, crawl, and monitor web pages with an easy command line tool
Browser Actbrowser-act/skills
AI agents use browser-act to automate web tasks like fetch forms screenshots and complex workflows
Firecrawlfirecrawl/cli
Search, scrape, and crawl websites with one simple command line tool
Playwright Climicrosoft/playwright-cli
Automate browser tasks and test web pages with simple terminal commands
Browser Usebrowser-use/browser-use
Automate web testing, form filling, and screenshots with simple CLI commands
Browser Act Skill Forgebrowser-act/skills
Explore any website once and create reusable skill packages forever